{"id":"W4387679928","doi":"10.4236/jgis.2023.155026","title":"Leveraging Geospatial Technology for Smallholder Farmer Credit Scoring","year":2023,"lang":"en","type":"article","venue":"Journal of Geographic Information System","topic":"Microfinance and Financial Inclusion","field":"Economics, Econometrics and Finance","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"International Development Research Centre; Styrelsen för Internationellt Utvecklingssamarbete","keywords":"Collateral; Food security; Business; Agriculture; Loan; Leverage (statistics); Access to finance; Geospatial analysis; Disadvantaged; Payment; Factoring; Agricultural economics; Economic growth; Geography; Finance; Economics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001354601,0.0001190447,0.0004042956,0.002124902,0.0002458108,0.00008008767,0.0002525322,0.0001650382,0.00001473424],"category_scores_gemma":[0.00009650621,0.0001237982,0.000224683,0.0009293519,0.00002880763,0.0009587202,0.00006824361,0.0001820163,0.0001791018],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008083128,"about_ca_system_score_gemma":0.00003237943,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002848026,"about_ca_topic_score_gemma":0.000001264865,"domain_scores_codex":[0.9981518,0.000005816476,0.001386405,0.00009814923,0.00007623995,0.0002815683],"domain_scores_gemma":[0.9980239,0.00002204662,0.001473254,0.0001610964,0.0002753203,0.00004438691],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002755958,0.00006478986,0.5710155,0.001576232,0.000334625,0.00002485903,0.006456225,0.002311936,0.0003380569,0.3757124,0.009700529,0.03218929],"study_design_scores_gemma":[0.00544254,0.0005887622,0.1307968,0.0009685628,0.00004774056,0.0003082645,0.007641213,0.01428028,0.000814373,0.01237254,0.8258376,0.000901307],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8676695,0.0004940631,0.1253733,0.0006423842,0.002704217,0.0003733291,0.00009715572,0.0001064941,0.002539627],"genre_scores_gemma":[0.9987254,0.0001366765,0.0006561446,0.00008926288,0.0002787218,0.00002116536,0.00001444684,0.00001121262,0.00006703291],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8161371,"threshold_uncertainty_score":0.5048345,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02724515859129054,"score_gpt":0.2158275234967644,"score_spread":0.1885823649054738,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}